--- title: "New Relic MCP server for AI agents - actionlake" description: "Give Claude 199 New Relic actions through one MCP server: alert violations, users. Your agent never holds the credential. 100,000 calls a month free." canonical: https://actionlake.com/connectors/new-relic updated: 2026-09-24 --- Connectors · Observability & analytics # New Relic MCP server for AI agents. actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to New Relic and the rest of your systems. It gives your agent 199 New Relic actions (69 reads, 90 writes and 40 that wait for a confirmation) and holds the New Relic credential itself, so the agent never does. It paces New Relic's limits and records every call. [Connect New Relic free](https://actionlake.com/console?start=sandbox) [See pricing](https://actionlake.com/pricing) 100,000 free calls a month. No card, no email, no password: press Start a free sandbox on the next screen and keep the key it shows you. `claude mcp add --transport http actionlake https://connect.actionlake.com/mcp` the first call ``` do { action: "newrelic.alert_violations.list", intent: "check which New Relic account is connected" } # List alert violations · read · 1 upstream call ``` - 199 actions in one signed file - 69 read look, never change - 90 write create and update - 40 wait for a yes destructive, confirmed first Set up ## Connect New Relic in three steps. 1. 01 ### Add actionlake to Claude. Run the command once in Claude Code; its consent page can create a free sandbox: 100,000 calls a month, no card. In the Claude app, add a custom connector with the URL below and paste your key on the consent page. Creating a new sandbox from the Claude app is not yet tested by us. `https://connect.actionlake.com/mcp` 2. 02 ### Connect New Relic. API key. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead. actionlake stores what you paste write-only, sealed under your tenant's key. - `api_key` New Relic user API key - `api_host` Where your New Relic lives: your api host ``` account { op: "connections.requirements", service: "newrelic" } # free: exactly what to paste, and what is found for you ``` 3. 03 ### Make the first call. Check before a write. Ask in plain words; Claude picks the action. Before anything changes, `check` validates the call and prices it, for free. ``` do { action: "newrelic.alert_violations.list" } # list alert violations · read · 1 upstream call check { action: "newrelic.users.user_create", input: { … } } # free: inputs, permissions, cost and confirmations, nothing sent ``` New Relic at a glance **Sign-in** API key. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead. **You provide** `api_key` **Setup fields** `api_host` **Limits we pace to** 1,000 calls a minute, per connection **API covered** New Relic API nerdgraph+rest_v2`api.newrelic.com` **Built from** New Relic's documentation, read 19 September 2026[api.newrelic.com](https://api.newrelic.com/docs/swagger.yml) [docs.newrelic.com](https://docs.newrelic.com/docs/apis/nerdgraph/get-started/introduction-new-relic-nerdgraph/) [docs.newrelic.com](https://docs.newrelic.com/docs/apis/intro-apis/new-relic-api-keys/) **Service file** Version 1.0.0, signed (Ed25519) **Cached reads** 68 of 69 reads, for up to an hour; a write clears what it affects **Ready-made plans** 8 in the store **Shared entities** 3, so ask can line New Relic up with your other systems **Data** Processed and stored in Sydney, Australia. No US region yet Capabilities ## What an AI agent can do in New Relic. 199 actions in 1 area. Every one carries its effect, so a key can allow the reads and hold the rest. - **69** read look, never change - **90** write create and update - **40** destructive wait for a confirmation 1. ### Monitoring 199 69 read · 90 write · 40 destructive List alert violations · List users · List APM applications · List alert incidents Top actions ## The New Relic API, shaped for agents. The ids your agent types, what each does, and the one name it shares with other systems. 96 of New Relic's 101 action names are shared with at least one other connector, so an agent learns them once. | Action | What it does | Effect | Same name in | | --- | --- | --- | --- | | `newrelic.alert_violations.list` List alert violations | Lists alert threshold violations over a time window. | read | `monitoring.alert.list` 51 connectors | | `newrelic.users.list` List users | Lists the users in an authentication domain, with their groups. | read | `identity.user.list` 474 connectors | | `newrelic.applications.list` List APM applications | Lists the APM applications reporting to this account. | read | `monitoring.service.list` 12 connectors | | `newrelic.alert_incidents.list` List alert incidents | Lists alert incidents for this account, newest first. | read | `monitoring.alert.list` 51 connectors | | `newrelic.users.user_create` Create a user | Creates a user in an authentication domain. | write | `identity.user.create` 262 connectors | | `newrelic.plugins.list` List plugins | Lists the Plugins (legacy product) registered in this account. | read | `monitoring.service.list` 12 connectors | | `newrelic.workloads.workload_create` Create a workload | Creates a workload, a named collection of entities whose health is rolled up together. | write | `monitoring.service.create` 11 connectors | | `newrelic.browser_applications.create` Create a browser application | Creates a standalone browser application and returns its monitoring key and loader script. | write | `monitoring.service.create` 11 connectors | | `newrelic.users.user_delete` Delete a user | Removes a user from the organisation. | destructive | `identity.user.delete` 253 connectors | | `newrelic.alert_conditions.list` List APM metric alert conditions | Lists the APM, browser and mobile metric conditions attached to one alert policy. | read | `monitoring.monitor.list` 32 connectors | | `newrelic.alert_nrql_conditions.list` List NRQL alert conditions | Lists the NRQL conditions attached to one alert policy. | read | `monitoring.monitor.list` 32 connectors | | `newrelic.alert_channels.list` List notification channels | Lists the alert notification channels in this account. | read | `monitoring.notification_channel.list` 18 connectors | Try it ## Prompts to paste into Claude. Each one names the New Relic actions it will call, so you know what it reads and what it changes before you send it. 1. Read read Which New Relic alerts are open right now? Group them by service. calls `newrelic.alert_violations.list` 2. Plan write Stand up an alert policy with a NRQL condition and a channel in New Relic. calls `newrelic.alert_policies.list` `newrelic.nrql.query` `newrelic.alert_policies.create` `newrelic.alert_nrql_conditions.create` `newrelic.alert_policy_channels.update` +1 more 3. Plan write Record a deployment then watch the application for fallout in New Relic. calls `newrelic.applications.get` `newrelic.deployments.create` `newrelic.applications.metric_data` `newrelic.alert_incidents.list` `newrelic.deployments.list` 4. Write write Create a user in New Relic. Show me exactly what you will send before you save it. calls `newrelic.users.user_create` The plan store ## Ready-made plans for New Relic. 8 plans in the store. Install one and your agent runs it by name; the reply says which connections are still missing. A schedule can run a plan on a timetable. There are no triggers or webhooks, by design. 1. ### Report the slowest hosts behind an application Use it when An application is slow overall and you need to know which of its hosts is dragging the average down. **Effect** read **Steps** 4 · loops **Needs** application id **Install** `newrelic-slow-hosts-report` 2. ### Tag every entity matching an entity search Use it when A group of entities found by an entity search query needs a common tag such as team, environment or cost centre. A person decides Add the supplied tags to _match count_ New Relic entities matching the search _query_. **Effect** write **Steps** 4 · loops **Needs** query and tags **Install** `newrelic-tag-entities-by-search` 3. ### Triage open alert incidents and acknowledge them Use it when An on-call engineer wants every open New Relic incident acknowledged and a list of what is currently firing. **Effect** write **Steps** 4 · loops **Install** `newrelic-triage-open-incidents` 4. ### Create a synthetic monitor and alert on its failures Use it when A public endpoint needs uptime checking from New Relic synthetics together with alerting when the checks fail. **Effect** write **Steps** 5 **Needs** account id, monitor name, url and policy id **Install** `newrelic-synthetic-monitor-rollout` 5. ### Record a deployment then watch the application for fallout Use it when A release has just gone out and you want it marked in New Relic and checked for immediate fallout. **Effect** write **Steps** 6 **Needs** application id and revision **Install** `newrelic-deploy-marker-and-watch` 6. ### Stand up an alert policy with a NRQL condition and a channel Use it when A new service needs alerting from scratch: a policy, a NRQL condition and somewhere for the notification to go. **Effect** write **Steps** 6 **Needs** account id, policy name, nrql and threshold **Install** `newrelic-new-alert-policy-with-nrql` 7. ### Retire an application that has stopped reporting Use it when An application has stopped reporting and you want it removed from New Relic after a human signs off. A person decides Permanently delete the New Relic application _name_ (id _application id_), which currently reports _number of items_ hosts. **Effect** destructive **Steps** 5 **Needs** application id **Install** `newrelic-retire-stale-application` 8. ### Mute alerts for a maintenance window Use it when Planned maintenance is about to start and alerts for the affected account should be silenced only for its duration. A person decides Silence New Relic alerts on account _account id_ with muting rule _rule name_ for a one hour maintenance window. **Effect** destructive **Steps** 6 **Needs** account id, rule name and condition **Install** `newrelic-mute-alerts-for-maintenance` install a plan ``` account { op: "plans.install", slug: "newrelic-slow-hosts-report" } # then ask for it by name; a schedule can run it on a timetable ``` Governance for New Relic ## Destructive actions wait for a yes. 40 New Relic actions are destructive. The first 10: - Delete a user `newrelic.users.user_delete` - Delete an APM application `newrelic.applications.delete` - Delete a workload `newrelic.workloads.workload_delete` - Delete an agent application (NerdGraph) `newrelic.agent_applications.agent_application_delete` - Delete a key transaction (NerdGraph) `newrelic.key_transactions_nerdgraph.key_transaction_delete` - Delete an APM metric alert condition `newrelic.alert_conditions.delete` - Delete an NRQL alert condition `newrelic.alert_nrql_conditions.delete` - Delete a Plugins alert condition `newrelic.alert_plugins_conditions.delete` - Delete a Synthetics alert condition `newrelic.alert_synthetics_conditions.delete` - Delete an external service alert condition `newrelic.alert_external_service_conditions.delete` A destructive action runs only with `confirm: true`. Under the `human` policy the agent cannot confirm for itself: the run stops until a named person approves, in the console or from a signed link in an email. The cap on a key is refused before the call is sent, never after. do newrelic.applications.delete confirm_policy: **human** Delete an APM application? **intent:** the user asked me to delete an APM application run suspended · waiting for a named person · key _newrelic-agent_ cannot confirm itself In the console, or from an emailed signed link. a key for this connector ``` account { op: "keys.create", name: "newrelic-agent", allowed_actions: ["newrelic.*"], cap_calls: 2000, confirm_policy: "human_for_writes", approval_rules: [ { match: "newrelic.users.user_delete", approver: "lead@example.com" }, { match: "newrelic.applications.delete", approver: "lead@example.com" }, { match: "newrelic.workloads.workload_delete", approver: "lead@example.com" } ] } ``` Illustrative. Scoped to New Relic only, capped at 2,000 upstream calls, every write confirmed, and the destructive ones approved by a named person. Cost ## What New Relic costs on actionlake. Every New Relic action is one upstream call, the only thing actionlake bills. Searching, `check`, `cost`, `account` and any call New Relic refused with 401, 403, 429 or a 5xx are free. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000. - 1 upstream call per action all 199 New Relic actions - 199 actions page each page of a long list is one call - 68 reads can be cached a cache hit costs nothing - 100,000 calls a month, free paid plans from US$49 a month for 250,000 [See pricing](https://actionlake.com/pricing) Action index ## Every New Relic action. 199 actions by area: the id your agent calls, what it does, and its effect. **Monitoring 199** - `newrelic.accounts.list` List accessible accounts read - `newrelic.agent_applications.agent_application_create_browser` Create a browser application (NerdGraph) write - `newrelic.agent_applications.agent_application_delete` Delete an agent application (NerdGraph) destructive - `newrelic.agent_applications.agent_application_settings_update` Update agent application settings (NerdGraph) write - `newrelic.alert_channels.create` Create a notification channel write - `newrelic.alert_channels.delete` Delete a notification channel destructive - `newrelic.alert_channels.list` List notification channels read - `newrelic.alert_conditions.create` Create an APM metric alert condition write - `newrelic.alert_conditions.delete` Delete an APM metric alert condition destructive - `newrelic.alert_conditions.list` List APM metric alert conditions read - `newrelic.alert_conditions.update` Update an APM metric alert condition write - `newrelic.alert_conditions_nerdgraph.alerts_condition_delete` Delete an alert condition (NerdGraph) destructive - `newrelic.alert_entity_conditions.add` Add an entity to an alert condition write - `newrelic.alert_entity_conditions.list` List alert conditions on an entity read - `newrelic.alert_entity_conditions.remove` Remove an entity from an alert condition destructive - `newrelic.alert_events.list` List alert events read - `newrelic.alert_external_service_conditions.create` Create an external service alert condition write - `newrelic.alert_external_service_conditions.delete` Delete an external service alert condition destructive - `newrelic.alert_external_service_conditions.list` List external service alert conditions read - `newrelic.alert_external_service_conditions.update` Update an external service alert condition write - `newrelic.alert_incidents.acknowledge` Acknowledge an alert incident write - `newrelic.alert_incidents.close` Close an alert incident write - `newrelic.alert_incidents.list` List alert incidents read - `newrelic.alert_location_failure_conditions.create` Create a multi-location Synthetics condition write - `newrelic.alert_location_failure_conditions.delete` Delete a multi-location Synthetics condition destructive - `newrelic.alert_location_failure_conditions.list` List multi-location Synthetics conditions read - `newrelic.alert_location_failure_conditions.update` Update a multi-location Synthetics condition write - `newrelic.alert_nrql_conditions.create` Create an NRQL alert condition write - `newrelic.alert_nrql_conditions.delete` Delete an NRQL alert condition destructive - `newrelic.alert_nrql_conditions.list` List NRQL alert conditions read - `newrelic.alert_nrql_conditions.update` Update an NRQL alert condition write - `newrelic.alert_nrql_conditions_nerdgraph.alerts_nrql_condition_baseline_create` Create a baseline NRQL alert condition (NerdGraph) write - `newrelic.alert_nrql_conditions_nerdgraph.alerts_nrql_condition_baseline_update` Update a baseline NRQL alert condition (NerdGraph) write - `newrelic.alert_nrql_conditions_nerdgraph.alerts_nrql_condition_static_create` Create a static NRQL alert condition (NerdGraph) write - `newrelic.alert_nrql_conditions_nerdgraph.alerts_nrql_condition_static_update` Update a static NRQL alert condition (NerdGraph) write - `newrelic.alert_nrql_conditions_nerdgraph.alerts_nrql_conditions_search` Search NRQL alert conditions (NerdGraph) read - `newrelic.alert_plugins_conditions.create` Create a Plugins alert condition write - `newrelic.alert_plugins_conditions.delete` Delete a Plugins alert condition destructive - `newrelic.alert_plugins_conditions.list` List Plugins alert conditions read - `newrelic.alert_plugins_conditions.update` Update a Plugins alert condition write - `newrelic.alert_policies.create` Create an alert policy write - `newrelic.alert_policies.delete` Delete an alert policy destructive - `newrelic.alert_policies.list` List alert policies read - `newrelic.alert_policies.update` Update an alert policy write - `newrelic.alert_policies_nerdgraph.alerts_policies_search` Search alert policies (NerdGraph) read - `newrelic.alert_policies_nerdgraph.alerts_policy_create` Create an alert policy (NerdGraph) write - `newrelic.alert_policies_nerdgraph.alerts_policy_delete` Delete an alert policy (NerdGraph) destructive - `newrelic.alert_policies_nerdgraph.alerts_policy_update` Update an alert policy (NerdGraph) write - `newrelic.alert_policy_channels.delete` Detach a notification channel from a policy destructive - `newrelic.alert_policy_channels.update` Attach notification channels to a policy write - `newrelic.alert_synthetics_conditions.create` Create a Synthetics alert condition write - `newrelic.alert_synthetics_conditions.delete` Delete a Synthetics alert condition destructive - `newrelic.alert_synthetics_conditions.list` List Synthetics alert conditions read - `newrelic.alert_synthetics_conditions.update` Update a Synthetics alert condition write - `newrelic.alert_violations.list` List alert violations read - `newrelic.api_access_keys.api_access_key_get` Get an API access key read - `newrelic.api_access_keys.create` Create API access keys write - `newrelic.api_access_keys.delete` Delete API access keys destructive - `newrelic.api_access_keys.update` Update API access keys write - `newrelic.application_hosts.get` Get an application host read - `newrelic.application_hosts.list` List hosts for an application read - `newrelic.application_hosts.metric_data` Get metric data for an application host read - `newrelic.application_hosts.metric_names` List metric names for an application host read - `newrelic.application_instances.get` Get an application instance read - `newrelic.application_instances.list` List instances for an application read - `newrelic.application_instances.metric_data` Get metric data for an application instance read - `newrelic.application_instances.metric_names` List metric names for an application instance read - `newrelic.applications.delete` Delete an APM application destructive - `newrelic.applications.get` Get an APM application read - `newrelic.applications.list` List APM applications read - `newrelic.applications.metric_data` Get metric data for an application read - `newrelic.applications.metric_names` List metric names for an application read - `newrelic.applications.update` Update an APM application write - `newrelic.browser_applications.create` Create a browser application write - `newrelic.browser_applications.list` List browser applications read - `newrelic.change_tracking.deployment_marker_create` Record a deployment (change tracking) write - `newrelic.cloud.configure_integration` Configure a cloud integration write - `newrelic.cloud.disable_integration` Disable a cloud integration write - `newrelic.cloud.link_account` Link a cloud account write - `newrelic.cloud.linked_accounts_list` List linked cloud accounts read - `newrelic.cloud.rename_account` Rename a linked cloud account write - `newrelic.cloud.unlink_account` Unlink a cloud account destructive - `newrelic.components.get` Get a plugin component read - `newrelic.components.list` List plugin components read - `newrelic.components.metric_data` Get metric data for a plugin component read - `newrelic.components.metric_names` List metric names for a plugin component read - `newrelic.dashboards.dashboard_create` Create a dashboard write - `newrelic.dashboards.dashboard_delete` Delete a dashboard destructive - `newrelic.dashboards.dashboard_get` Get a dashboard read - `newrelic.dashboards.dashboard_snapshot_url_create` Create a dashboard snapshot URL write - `newrelic.dashboards.dashboard_update` Update a dashboard write - `newrelic.deployments.create` Record a deployment marker write - `newrelic.deployments.delete` Delete a deployment marker destructive - `newrelic.deployments.list` List deployment markers read - `newrelic.entities.entity_get` Get an entity by GUID read - `newrelic.entities.entity_search` Search entities read - `newrelic.entities.get_batch` Get several entities by GUID read - `newrelic.groups.group_create` Create a user group write - `newrelic.groups.group_delete` Delete a user group destructive - `newrelic.groups.group_update` Update a user group write - `newrelic.groups.group_users_add` Add users to groups write - `newrelic.groups.group_users_remove` Remove users from groups destructive - `newrelic.groups.list` List user groups read - `newrelic.insights.query` Run an NRQL query through the Insights query API read - `newrelic.key_transactions.get` Get a key transaction read - `newrelic.key_transactions.list` List key transactions read - `newrelic.key_transactions_nerdgraph.key_transaction_create` Create a key transaction (NerdGraph) write - `newrelic.key_transactions_nerdgraph.key_transaction_delete` Delete a key transaction (NerdGraph) destructive - `newrelic.key_transactions_nerdgraph.key_transaction_update` Update a key transaction (NerdGraph) write - `newrelic.labels.delete` Delete a label destructive - `newrelic.labels.list` List labels read - `newrelic.labels.upsert` Create or update a label write - `newrelic.log_data_partition_rules.list` List log data partition rules read - `newrelic.log_data_partition_rules.log_data_partition_rule_create` Create a log data partition rule write - `newrelic.log_data_partition_rules.log_data_partition_rule_delete` Delete a log data partition rule destructive - `newrelic.log_data_partition_rules.log_data_partition_rule_update` Update a log data partition rule write - `newrelic.log_obfuscation.expression_create` Create a log obfuscation expression write - `newrelic.log_obfuscation.expression_delete` Delete a log obfuscation expression destructive - `newrelic.log_obfuscation.expression_update` Update a log obfuscation expression write - `newrelic.log_obfuscation.expressions_list` List log obfuscation expressions read - `newrelic.log_obfuscation.rule_create` Create a log obfuscation rule write - `newrelic.log_obfuscation.rule_delete` Delete a log obfuscation rule destructive - `newrelic.log_obfuscation.rule_update` Update a log obfuscation rule write - `newrelic.log_obfuscation.rules_list` List log obfuscation rules read - `newrelic.log_parsing_rules.list` List log parsing rules read - `newrelic.log_parsing_rules.log_grok_test` Test a Grok pattern against log lines read - `newrelic.log_parsing_rules.log_parsing_rule_create` Create a log parsing rule write - `newrelic.log_parsing_rules.log_parsing_rule_delete` Delete a log parsing rule destructive - `newrelic.log_parsing_rules.log_parsing_rule_update` Update a log parsing rule write - `newrelic.mobile_applications.get` Get a mobile application read - `newrelic.mobile_applications.list` List mobile applications read - `newrelic.mobile_applications.metric_data` Get metric data for a mobile application read - `newrelic.mobile_applications.metric_names` List metric names for a mobile application read - `newrelic.muting_rules.list` List alert muting rules read - `newrelic.muting_rules.muting_rule_create` Create an alert muting rule write - `newrelic.muting_rules.muting_rule_delete` Delete an alert muting rule destructive - `newrelic.muting_rules.muting_rule_get` Get an alert muting rule read - `newrelic.muting_rules.muting_rule_update` Update an alert muting rule write - `newrelic.nerdgraph.query` Run any NerdGraph GraphQL query read - `newrelic.notification_channels.list` List notification channels read - `newrelic.notification_channels.notification_channel_create` Create a notification channel write - `newrelic.notification_channels.notification_channel_delete` Delete a notification channel destructive - `newrelic.notification_channels.notification_channel_update` Update a notification channel write - `newrelic.notification_destinations.list` List notification destinations read - `newrelic.notification_destinations.notification_destination_create` Create a notification destination write - `newrelic.notification_destinations.notification_destination_delete` Delete a notification destination destructive - `newrelic.notification_destinations.notification_destination_update` Update a notification destination write - `newrelic.nrql.query` Run an NRQL query read - `newrelic.nrql_drop_rules.create` Create NRQL drop rules write - `newrelic.nrql_drop_rules.delete` Delete NRQL drop rules destructive - `newrelic.nrql_drop_rules.list` List NRQL drop rules read - `newrelic.plugins.get` Get a plugin read - `newrelic.plugins.list` List plugins read - `newrelic.service_levels.list` List service level indicators read - `newrelic.service_levels.service_level_create` Create a service level indicator write - `newrelic.service_levels.service_level_delete` Delete a service level indicator destructive - `newrelic.service_levels.service_level_update` Update a service level indicator write - `newrelic.synthetics_monitors.synthetics_monitor_broken_links_create` Create a Synthetics broken links monitor write - `newrelic.synthetics_monitors.synthetics_monitor_broken_links_update` Update a Synthetics broken links monitor write - `newrelic.synthetics_monitors.synthetics_monitor_cert_check_create` Create a Synthetics certificate check monitor write - `newrelic.synthetics_monitors.synthetics_monitor_cert_check_update` Update a Synthetics certificate check monitor write - `newrelic.synthetics_monitors.synthetics_monitor_delete` Delete a Synthetics monitor destructive - `newrelic.synthetics_monitors.synthetics_monitor_script_api_create` Create a Synthetics scripted API monitor write - `newrelic.synthetics_monitors.synthetics_monitor_script_api_update` Update a Synthetics scripted API monitor write - `newrelic.synthetics_monitors.synthetics_monitor_script_browser_create` Create a Synthetics scripted browser monitor write - `newrelic.synthetics_monitors.synthetics_monitor_script_browser_update` Update a Synthetics scripted browser monitor write - `newrelic.synthetics_monitors.synthetics_monitor_simple_browser_create` Create a Synthetics simple browser monitor write - `newrelic.synthetics_monitors.synthetics_monitor_simple_browser_update` Update a Synthetics simple browser monitor write - `newrelic.synthetics_monitors.synthetics_monitor_simple_create` Create a Synthetics ping monitor write - `newrelic.synthetics_monitors.synthetics_monitor_simple_update` Update a Synthetics ping monitor write - `newrelic.synthetics_monitors.synthetics_monitor_step_create` Create a Synthetics step monitor write - `newrelic.synthetics_monitors.synthetics_monitor_step_update` Update a Synthetics step monitor write - `newrelic.synthetics_monitors.synthetics_script_get` Get a Synthetics monitor script read - `newrelic.synthetics_monitors.synthetics_steps_get` Get a Synthetics step monitor's steps read - `newrelic.synthetics_private_locations.synthetics_private_location_create` Create a Synthetics private location write - `newrelic.synthetics_private_locations.synthetics_private_location_delete` Delete a Synthetics private location destructive - `newrelic.synthetics_private_locations.synthetics_private_location_purge_queue` Purge a Synthetics private location queue destructive - `newrelic.synthetics_private_locations.synthetics_private_location_update` Update a Synthetics private location write - `newrelic.synthetics_secure_credentials.synthetics_secure_credential_create` Create a Synthetics secure credential write - `newrelic.synthetics_secure_credentials.synthetics_secure_credential_delete` Delete a Synthetics secure credential destructive - `newrelic.synthetics_secure_credentials.synthetics_secure_credential_update` Update a Synthetics secure credential write - `newrelic.tags.add` Add tags to an entity write - `newrelic.tags.delete` Delete tag keys from an entity destructive - `newrelic.tags.replace` Replace all tags on an entity write - `newrelic.tags.tag_values_delete` Delete specific tag values from an entity destructive - `newrelic.users.list` List users read - `newrelic.users.user_create` Create a user write - `newrelic.users.user_current_get` Get the authenticated user read - `newrelic.users.user_delete` Delete a user destructive - `newrelic.users.user_update` Update a user write - `newrelic.workflows.list` List alert workflows read - `newrelic.workflows.workflow_create` Create an alert workflow write - `newrelic.workflows.workflow_delete` Delete an alert workflow destructive - `newrelic.workflows.workflow_update` Update an alert workflow write - `newrelic.workloads.workload_create` Create a workload write - `newrelic.workloads.workload_delete` Delete a workload destructive - `newrelic.workloads.workload_duplicate` Duplicate a workload write - `newrelic.workloads.workload_get` Get a workload read - `newrelic.workloads.workload_update` Update a workload write Questions ## The New Relic MCP server, answered. **Is there a New Relic MCP server for Claude?** Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 199 New Relic actions, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by New Relic. **What do I need to connect New Relic?** New Relic user API key. Plus your api host. The free call account { op: "connections.requirements", service: "newrelic" } lists exactly what to paste. **Can an AI agent delete or change things in New Relic?** Only if its key allows it, and only with an explicit confirmation. 40 New Relic actions are destructive, including delete a user, delete an APM application and delete a workload. Each runs only with confirm: true. Under the human confirm policy, or an approval rule on the key, the run waits until a named person approves it. **Will an AI agent use up my New Relic API limit?** actionlake paces every call to the limits in the New Relic service file: 1,000 calls a minute per connection. Repeated reads are answered from cache (68 New Relic actions can be), which never reaches New Relic. **What does a New Relic action cost?** One upstream call, the only unit actionlake bills. A list that pages bills one call per page (199 New Relic actions page). Cache hits, searches, dry runs and calls New Relic refused with 401, 403, 429 or a 5xx are free. The Free plan includes 100,000 calls a month with no card. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000. **Which New Relic API does it cover?** The New Relic API nerdgraph+rest_v2 at api.newrelic.com by default, or the base URL set when you connect. It is built from New Relic's documentation as read on 19 September 2026. 199 actions in 1 area, each one in the signed service file (version 1.0.0). **Does actionlake keep my New Relic data, and where?** actionlake processes and stores data in Sydney, Australia; there is no US region yet. Reads may be cached for up to an hour, and a write clears the reads it affects. Each run's request and response is kept, sealed, for your plan's trace window: 1 day on Free, 3 days on Starter, 7 days on Pro, 14 days on Team, 30 days on Business and 30 days on Enterprise. Your New Relic credential is sealed under your tenant's key, never logged and never returned. Your traffic is not used to train models. **Which AI clients can use it?** Claude Code, tested by us end to end, and the Claude app as a custom connector, tested by us with an existing key. Other MCP clients that support remote servers over Streamable HTTP (MCP revisions 2025-06-18 and 2025-11-25) and OAuth dynamic client registration, or a bearer header, should connect the same way; we have not tested them. Or plain REST, under the same action names. ## More connectors like New Relic Shares the most action names with - [Datadog 68](https://actionlake.com/connectors/datadog) - [Grafana 46](https://actionlake.com/connectors/grafana) - [Google Cloud Monitoring 32](https://actionlake.com/connectors/google-cloud-monitoring) - [Dynatrace 27](https://actionlake.com/connectors/dynatrace) - [Axiom 26](https://actionlake.com/connectors/axiom) - [Uptrends 24](https://actionlake.com/connectors/uptrends) Joins with, on shared entities - [Rootly 3](https://actionlake.com/connectors/rootly) - [FireHydrant 3](https://actionlake.com/connectors/firehydrant) - [PagerDuty 3](https://actionlake.com/connectors/pagerduty) - [ilert 3](https://actionlake.com/connectors/ilert) - [Zabbix 3](https://actionlake.com/connectors/zabbix) - [NinjaOne 2](https://actionlake.com/connectors/ninjaone) Browse - [All Observability & analytics connectors](https://actionlake.com/connectors/category/observability-and-analytics) - [All connectors](https://actionlake.com/connectors) - [How actionlake compares](https://actionlake.com/compare) actionlake is independent. It is not made or endorsed by New Relic; the name is the vendor's own. Counts are from the New Relic service file, version 1.0.0. ## Give your agent New Relic today. [Connect New Relic free](https://actionlake.com/console?start=sandbox) [See pricing](https://actionlake.com/pricing) Start free - 100,000 calls/month, no card. No signup. Hard caps on every key. Cached answers are free. --- Source: https://actionlake.com/connectors/new-relic More: https://actionlake.com/llms.txt